iSEE: Object Permanence Through Self-Supervision
Research
Research News
New papers, breakthroughs and academic AI research
Towards Reliable Vision-Language Models for Autonomous Driving
Research
Measuring the Stability Assumption Behind Action Chunking
Research
FlashBack: Knowing When to Remember in Streaming Vision-Language Models
Research
NextMe-800: Anticipating Personal Behavior from Months of Egocentric Video
Research
Neither Black nor White: Balancing Semantic and Collaborative Signals with Graph-Informed Semantic IDs (GrIS)
Research
Agents Are Systems, Not Models: Rethinking Agentic Evaluation
Research
CoEvolve: Construct-to-Edit Visual Grounding with Bidirectional State Refinement
Research
When Does a Second Model Help? Cross-Model Review in LLM Verification
Research
The Persona Is Still There, but Who Is Speaking? Latent Identity Reversion in Persistent AI Agents
Research
Auditing Web Agent Evaluation on WebArena-Lite: Human Review of Outcomes and Trajectories
Research
No Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning Collapse
Research